AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning

Peixi Peng, Yonghong Tian, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Tiejun Huang

TPAMI 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 93 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add discriminative latent attributes Dd (ablation)joint attribute dictionary model · AwA ZSLaccuracy (%): 81.6 -> 82.9Improved
add discriminative latent attributes Dd (ablation)joint attribute dictionary model · CUB ZSLaccuracy (%): 50.7 -> 57.1Improved
add background latent attributes Db (ablation)joint attribute dictionary model · AwA ZSLaccuracy (%): 80.2 -> 82.9Improved
add background latent attributes Db (ablation)joint attribute dictionary model · CUB ZSLaccuracy (%): 48.9 -> 57.1Improved
model a linear transformation W from user-defined attributes to the dictionary subspace (ablation)joint attribute dictionary model · AwA ZSLaccuracy (%): 74.4 -> 82.9Improved
model a linear transformation W from user-defined attributes to the dictionary subspace (ablation)joint attribute dictionary model · CUB ZSLaccuracy (%): 42.6 -> 57.1Improved
add latent attributes Dd to improve user-defined attribute prediction (ablation)joint attribute dictionary model · CUB attribute predictionmAUC (%): 74.4 -> 78.3Improved
add transformation W to improve attribute prediction (ablation)joint attribute dictionary model · AwA attribute predictionmAUC (%): 68.9 -> 75.8Improved
add latent attributes to user-defined attributes for Re-ID (ablation)Ours (LOMO features) · VIPeR (supervised)rank-1 (%): 41.5 -> 44.3Improved
use only user-defined attributes instead of latent attributes (ablation)Ours (LOMO features) · VIPeR (supervised)rank-1 (%): 41.5 -> 17.1Hurt
add user-defined attributes to latent attributes for Re-ID (ablation)Ours (LOMO features) · PRID (supervised)rank-1 (%): 28.9 -> 31.8Improved
replace LOMO features with GoogLeNet CNN featuresOurs L · VIPeR (supervised)rank-1 (%): 41.5 -> 49.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy